Haoli Bai

Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation

ATTS: Asynchronous Test-Time Scaling via Conformal Prediction

MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents

Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents

InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search

FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension

Dr.Mi-Bench: A Modular-integrated Benchmark for Scientific Deep Research Agent

E$^3$-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models

ModalMix: Optimizing Multimodal Data Mixtures with Compute-Dependent Regression

Benchmarking and Advancing Quantization-Aware Training for Reasoning Models

DualRPO: All-in-one Visual RL with Internal and External Rewards

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models

FlatQuant: Flatness Matters for LLM Quantization

A Simple Linear Patch Revives Layer-Pruned Large Language Models

FreqKV: Frequency Domain Key-Value Compression for Efficient Context Window Extension

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

FlatQuant: Flatness Matters for LLM Quantization